Activity-Informed Industrial Audio Anomaly Detection Via Source Separation
- Title
- Activity-Informed Industrial Audio Anomaly Detection Via Source Separation
- Authors
- Kim, JAECHANG; YUNJOO, LEE; Cho, Hyun Mi; Kim, Dong Woo; Song, Chi Hoon; Ok, Jungseul
- Date Issued
- 2023-06-06
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Abstract
- We discuss a practical scenario of anomaly detection for industrial sound data where the sound of a target machine is corrupted by not only noise from plant environments but also interference from neighboring machines. This is particularly challenging since the interfering sounds are virtually indistinguishable from the target machine without additional information. To overcome these challenges, we fully exploit the information of machine activity or control that is easy to obtain in the industrial environment, and propose a framework of source separation (SS) followed by anomaly detection (AD), so called SSAD. We note that the proposed SSAD utilizes the activity information for not only AD but also SS. In our experiment based on industrial dataset, we demonstrate that the proposed method using only mixture signal and activity information achieves comparable accuracy with an oracle baseline using clean source signals.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/119850
- Article Type
- Conference
- Citation
- 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023, 2023-06-06
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.